论文检索

Yajie Liu, Jinjin Zhang, Qingjie Liu, Di Huang

Large-scale vision-language models (VLMs) such as CLIP have excelled in zero-shot image classification, yet they struggle to achieve the dense cross-modal alignment required by open-vocabulary dense perception (OVDP). While recent self-distillation methods address this by aligning dense features with the generalizable global semantics, a key question remains: how should such dense features be constructed to achieve optimal alignment? To address this, we propose DenseRC, a principled Dense Representations Construction framework that reconstructs CLIP for OVDP based on two key insights.First, by analyzing the internal semantics encoded in the global cls token, we identify that multi-layer value embeddings serve as an informative basis for dense features. Second, we reveal that spatial aggregation tends to amplify semantic misalignment. Motivated by this, we design a lightweight Head-Selective Gating (HSG) module that adaptively reweights feature heads according to their intrinsic heterogeneity, enabling discriminative and alignment-friendly dense representations construction. Extensive experiments demonstrate that DenseRC delivers consistent and substantial gains across OVDP tasks including object detection and semantic segmentation, setting new state-of-the-art performance on multiple benchmarks.

Jiyoung Lim, Heejae Yang, Jee-Hyong Lee

Composed Image Retrieval (CIR) aims to retrieve target images by integrating a reference image with a corresponding modification text. CIR requires jointly considering the explicit semantics specified in the query and the implicit semantics embedded within its bi-modal composition. Recent training-free Zero-Shot CIR (ZS-CIR) methods leverage Multimodal Large Language Models (MLLMs) to generate detailed target descriptions, converting the implicit information into explicit textual expressions. However, these methods rely heavily on the textual modality and fail to capture the fuzzy retrieval nature that requires considering diverse combinations of candidates. This leads to reduced diversity and accuracy in retrieval results. To address this limitation, we propose a novel training-free method, Geodesic Mixup-based Implicit semantic eXpansion and Explicit semantic Re-ranking for ZS-CIR (G-MIXER). G-MIXER constructs composed query features that reflect the implicit semantics of reference image-text pairs through geodesic mixup over a range of mixup ratios, and builds a diverse candidate set. The generated candidates are then re-ranked using explicit semantics derived from MLLMs, improving both retrieval diversity and accuracy. Our proposed G-MIXER achieves state-of-the-art performance across multiple ZS-CIR benchmarks, effectively handling both implicit and explicit semantics without additional training. Our code will be available at https://github.com/maya0395/gmixer.

Shenyin Xu, Yishan Wang, Xinyu Li, Rui Liu, Zhongyuan Wang, Xin Tian

3D LiDAR-based gait recognition has gained increasing attention due to its robustness to illumination, privacy preservation, and capability for long-range and non-contact identity verification. However, existing point cloud-based methods suffer from two critical limitations: they fail to model semantically distant correlations across spatial scales and employ simplistic temporal aggregation that cannot handle gait's inherent heterogeneity. To address these limitations, we propose MS^2Gait, a multi-scale spatio-temporal framework tailored for raw point cloud gait recognition. Our Hierarchical Spatial Feature Extraction module introduces four complementary interaction strategies to explicitly capture long-range semantic dependencies and recover structural information under blockage. Additionally, a Similarity-based Temporal Enhancement Transformer strategy leverages multi-scale aggregation to dynamically weight frames based on motion coherence, effectively handling temporal heterogeneity without explicit supervision. Extensive evaluations on SUSTech1K and FreeGait demonstrate that MS^2Gait achieves 93.5% and 83.1% in Rank-1 accuracy, respectively, outperforming prior state-of-the-art methods, while exhibiting significant robustness against non-gait nuisance factors.

Yiyu Wang, Xuyang Liu, Xiyan Gui, Xinying Lin, Boxue Yang, Chenfei Liao, Tailai Chen, Linfeng Zhang

Streaming Video Large Language Models (VideoLLMs) have demonstrated impressive performance across various video understanding tasks, but they face significant challenges in real-time deployment due to the high computational cost of processing dense visual tokens from continuous video streams. In streaming video scenarios, the primary bottleneck lies in the Vision Transformer (ViT) encoding stage, where redundant processing of temporally similar frames leads to inefficiency. Additionally, inflated token sequences during LLM pre-filling further exacerbate latency and memory overhead. To address these challenges, we propose Streaming Token Compression (STC), a plug-and-play hierarchical framework that seamlessly integrates into existing streaming VideoLLMs, optimizing both ViT encoding and LLM pre-filling stages to accelerate processing. STC introduces two token-level accelerators: STC-Cacher, which reduces ViT encoding overhead by caching and reusing features from temporally similar frames, and STC-Pruner, which compresses the visual token sequence before it enters the LLM, preserving only the most salient tokens based on both spatial and temporal relevance. Extensive experiments on four baseline streaming VideoLLMs across five benchmarks demonstrate that STC outperforms other compression methods. Notably, STC retains up to 99% of accuracy on the ReKV framework while reducing ViT encoding latency and LLM pre-filling latency by 24.5% and 45.3%.

Zeyu Jiang, Lai Man Po, Xuyuan Xu, Yexin Wang, Guoping Gong, Haoxuan Wu, Chenbo Yan, Kun Li, Yuyang Liu

Multimodal image synthesis has made significant progress, yet most editing methods still rely on textual instructions, which are less direct than visual guidance. Recently, a new paradigm edits one image using another as reference, enabling more intuitive manipulation through visual exemplars. We formalize this setting as cross-image editing, where a source image is modified under one or more visual references. We propose OrionEdit, a unified framework that regulates editing via symmetric orthogonal subspace disentanglement and reverse-causal attention with information-flow masks enforcing unidirectional latent dependencies. Built on standard diffusion backbones, OrionEdit enables zero-shot multi-reference editing and outperforms open-source baselines, approaching proprietary models in fidelity and disentanglement. The model is available at https://github.com/cityuhkai/OrionEdit.

Yifan Xu, Chao Zhang, Ruifei Ma, Fei Gao, Zhifei Yang, Jiaxing Qi, Zhipeng Chen

The new era has witnessed a remarkable capability to extend Vision-Language Models (VLMs) for tackling tasks of video understanding. While current VLMs excel at event- or story-level understanding, their ability to capture fine-grained motion details remains limited, primarily due to their focus on high-level static semantic structures and macro-event logic. In contrast, Video Diffusion Models (VDMs) are adept at modeling dynamic motion patterns, benefiting from large-scale video data and the intrinsic requirement of temporal generation. In this paper, we introduce MotionEnhancer, a novel approach that leverages motion priors distilled from a powerful video diffusion model as auxiliary supervision to enhance the motion understanding capability of a VLM via attention alignment. MotionEnhancer comprises two simple parameter-free modules, Motion-sensitive Head Selection (MHS) and Motion-salient Text Token Identification (MTTI), to directly extract and optimize motion-related attentions from the VDM in a computation-only manner. MotionEnhancer provides a scalable solution for motion understanding without additional training parameters, modifications to existing architectures, or tool calling. Extensive experiments demonstrate that MotionEnhancer can achieve consistent improvements over state-of-the-art VLMs on two motion-level video understanding benchmarks, especially on motion-related metrics.

Yang-Tian Sun, Zehuan Huang, Yifan Niu, Lin Ma, Yan-Pei Cao, Yuewen Ma, Xiaojuan Qi

We present StereoWorld, a camera-conditioned stereo world model that jointly learns appearance and binocular geometry for end-to-end stereo video generation.Unlike monocular RGB or RGBD approaches, StereoWorld operates exclusively within the RGB modality, while simultaneously grounding geometry directly from disparity. To efficiently achieve consistent stereo generation, our approach introduces two key designs: (1) a unified camera-frame RoPE that augments latent tokens with camera-aware rotary positional encoding, enabling relative, view- and time-consistent conditioning while preserving pretrained video priors via a stable attention initialization; and (2) a stereo-aware attention decomposition that factors full 4D attention into 3D intra-view attention plus horizontal row attention, leveraging the epipolar prior to capture disparity-aligned correspondences with substantially lower compute. Across benchmarks, StereoWorld improves stereo consistency, disparity accuracy, and camera-motion fidelity over strong monocular-then-convert pipelines, achieving more than 3x faster generation with an additional 5% gain in viewpoint consistency. Beyond benchmarks, StereoWorld enables end-to-end binocular VR rendering without depth estimation or inpainting, enhances embodied policy learning through metric-scale depth grounding, and is compatible with long-video distillation for extended interactive stereo synthesis.

Xi Chen, Maojun Zhang, Yu Liu, Shen Yan

Domain Generalization Semantic Segmentation (DGSS) in spectral remote sensing is severely challenged by spectral shifts across diverse acquisition conditions, which cause significant performance degradation for models deployed in unseen domains. While fine-tuning foundation models is a promising direction, existing methods employ global, homogeneous adjustments. This "one-size-fits-all" tuning struggles with the spatial heterogeneity of land cover, causing semantic confusion. We argue that the key to robust DGSS lies not in a single global adaptation, but in performing fine-grained, spatially-adaptive refinement of a foundation model's features. To achieve this, we propose SpectralMoE, a novel fine-tuning framework for DGSS. It operationalizes this principle by utilizing a Mixture-of-Experts (MoE) architecture to perform local precise refinement on the foundation model's features, incorporating depth features estimated from selected RGB bands of the spectral remote sensing imagery to guide the fine-tuning process. Specifically, SpectralMoE employs a dual-gated MoE architecture that independently routes visual and depth features to top-k selected experts for specialized refinement, enabling modality-specific adjustments. A subsequent cross-attention mechanism then judiciously fuses the refined structural cues into the visual stream, mitigating semantic ambiguities caused by spectral variations. Extensive experiments show that SpectralMoE sets a new state-of-the-art on multiple DGSS benchmarks across hyperspectral, multispectral, and RGB remote sensing imagery.

Yuhan Chen, Pengwen Dai, Chuan Wang, Dayan Wu, Xiaochun Cao

Text-video retrieval tasks have seen significant improvements due to the recent development of large-scale vision-language pre-trained models. Traditional methods primarily focus on video representations or cross-modal alignment, while recent works shift toward enriching text expressiveness to better match the rich semantics in videos. However, these methods use only interactions between text and frames/video, and ignore rich interactions among the internal frames within a video, so the final expanded text cannot capture frame contextual information, leading to disparities between text and video. In response, we introduce Energy-Aware Fine-Grained Relationship Learning Network (EagleNet) to generate accurate and context-aware enriched text embeddings. Specifically, the proposed Fine-Grained Relationship Learning mechanism (FRL) first constructs a text-frame graph by the generated text candidates and frames, then learns relationships among texts and frames, which are finally used to aggregate text candidates into an enriched text embedding that incorporates frame contextual information. To further improve fine-grained relationship learning in FRL, we design Energy-Aware Matching (EAM) to model the energy of text-frame interactions and thus accurately capture the distribution of real text-video pairs. Moreover, for more effective cross-modal alignment and stable training, we replace the conventional softmax-based contrastive loss with the sigmoid loss. Extensive experiments have demonstrated the superiority of EagleNet across MSRVTT, DiDeMo, MSVD, and VATEX.

Yutian Chen, Yuheng Qiu, Ruogu Li, Jay Patrikar, Sebastian Scherer

We propose Confidence-Guided Token Merging (Co-Me), an acceleration mechanism for visual geometric transformers without retraining or finetuning the base model. Co-Me distilled a light-weight confidence predictor to rank tokens by uncertainty and selectively merge low-confidence ones, effectively reducing computation while maintaining spatial coverage. Compared to similarity-based merging or pruning, the confidence signal in Co-Me reliably indicates regions emphasized by the transformer, enabling substantial acceleration without degrading performance. Co-Me applies seamlessly to various multi-view and streaming visual geometric transformers, achieving speedups that scale with sequence length. When applied to VGGT and Pi3, Co-Me achieves up to 21.5x and 20.4x speedup, making visual geometric transformers practical for real-time 3D perception and reconstruction.

Zilong Zhao, Zhengming Ding, Pei Niu, Wenhao Sun, Feng Guo

Feature encoders play a key role in pixel-level crack segmentation by shaping the representation of fine textures and thin structures. Existing CNN-, Transformer-, and Mamba-based models each capture only part of the required spatial or structural information, leaving clear gaps in modeling complex crack patterns. To address this, we present MixerCSeg, a mixer architecture designed like a coordinated team of specialists, where CNN-like pathways focus on local textures, Transformer-style paths capture global dependencies, and Mamba-inspired flows model sequential context within a single encoder. At the core of MixerCSeg is the TransMixer, which explores Mamba's latent attention behavior while establishing dedicated pathways that naturally express both locality and global awareness. To further enhance structural fidelity, we introduce a spatial block processing strategy and a Direction-guided Edge Gated Convolution (DEGConv) that strengthens edge sensitivity under irregular crack geometries with minimal computational overhead. A Spatial Refinement Multi-Level Fusion (SRF) module is then employed to refine multi-scale details without increasing complexity. Extensive experiments on multiple crack segmentation benchmarks show that MixerCSeg achieves state-of-the-art performance with only 2.05 GFLOPs and 2.54 M parameters, demonstrating both efficiency and strong representational capability. The code is available at https://github.com/spiderforest/MixerCSeg.

Joonki Min, Chaeyun Kim, Hyungwook Choi, Yejin Kim, Kihyun Kim, Yohan Jo, Joonseok Lee

Multimodal Large Language Models (MLLMs) are increasingly deployed in multi-image scenarios requiring complex reasoning across visual contexts. However, current MLLMs remain fundamentally limited by object hallucination--generating plausible yet factually inconsistent descriptions about objects. Existing benchmarks, designed primarily for single-image settings or providing only high-level multi-image assessments, cannot systematically diagnose how visual complexity and reasoning demands trigger hallucination. To address this gap, we introduce MIOH, a fine-grained multi-image object hallucination benchmark that systematically evaluates object hallucination across four foundational tasks (existence, counting, attribute, position) through three multi-image reasoning patterns (comprehensive, comparative, selective) under three controlled adversarial pressures (visual context scale, perceptual difficulty, contextual bias). Through evaluation of 29 models, we reveal that even state-of-the-art systems like GPT-5 and Gemini-2.5-Pro exhibit distinct failure patterns across different reasoning patterns and tasks. Our evaluation reveals that hallucination stems not merely from perceptual failures but from integration-stage limitations when maintaining object representations across multiple images. MIOH provides a controlled framework for analyzing multi-image object hallucination and serves as a critical evaluation tool for developing more reliable multimodal AI systems.

Aishwarya Agarwal, Srikrishna Karanam, Vineet Gandhi

Contrastive vision-language models (VLMs) such as CLIP achieve strong zero-shot recognition yet remain vulnerable to spurious correlations, particularly background over-reliance. We introduce Cluster-based Concept Importance (CCI), a novel interpretability method that uses CLIP's own patch embeddings to group spatial patches into semantically coherent clusters, masking them, and evaluating relative changes in model predictions. CCI sets a new state of the art on faithfulness benchmarks, surpassing prior methods by large margins; for example, it yields more than a twofold improvement on the deletion-AUC metric for MS COCO retrieval. We further propose that CCI when combined with GroundedSAM, automatically categorizes predictions as foreground or background-driven, providing a crucial diagnostic ability. Existing benchmarks such as CounterAnimals, however, rely solely on accuracy and implicitly attribute all performance degradation to background correlations. Our analysis shows this assumption to be incomplete, since many errors arise from viewpoint variation, scale shifts, and fine-grained object confusions. To disentangle these effects, we introduce COVAR, a benchmark that systematically varies object foregrounds and backgrounds. Leveraging CCI with COVAR, we conduct a comprehensive evaluation of eighteen CLIP variants, providing both methodological advances and empirical evidence that chart a path toward more robust vision-language models.

Wentao Qu, Guofeng Mei, Yang Wu, YongShun Gong, Xiaoshui Huang, Liang Xiao

Text-to-LiDAR generation can customize 3D data with rich structures and diverse scenes for downstream tasks. However, the scarcity of Text-LiDAR pairs often causes insufficient training priors, generating overly smooth 3D scenes. Moreover, low-quality text descriptions may degrade generation quality and controllability. In this paper, we propose a Text-to-LiDAR Diffusion Model for scene generation, named T2LDM, with a Self-Conditioned Representation Guidance (SCRG). Specifically, SCRG, by aligning to the real representations, provides the soft supervision with reconstruction details for the Denoising Network (DN) in training, while decoupled in inference. In this way, T2LDM can perceive rich geometric structures from data distribution, generating detailed objects in scenes. Meanwhile, we construct a content-composable Text-LiDAR benchmark, T2nuScenes, along with a controllability metric. Based on this, we analyze the effects of different text prompts for LiDAR generation quality and controllability, providing practical prompt paradigms and insights. Furthermore, a directional position prior is designed to mitigate street distortion, further improving scene fidelity. Additionally, by learning a conditional encoder via frozen DN, T2LDM can support multiple conditional tasks, including Sparse-to-Dense, Dense-to-Sparse, and Semantic-to-LiDAR generation. Extensive experiments in unconditional and conditional generation demonstrate that T2LDM outperforms existing methods, achieving state-of-the-art scene generation.

Weiqing Li, Jinyue Guo, Yaqi Wang, Haiyang Xiao, Yuewei Zhang, Guohua Liu, Hao Henry Wang

Visual-language models (VLMs) excel at data mappings, but real-world document heterogeneity and unstructuredness disrupt the consistency of cross-modal embeddings. Recent late-interaction methods enhance image-text alignment through multi-vector representations, yet traditional training with limited samples and static strategies cannot adapt to the model's dynamic evolution, causing cross-modal retrieval confusion. To overcome this, we introduce Evo-Retriever, a retrieval framework featuring an LLM-guided curriculum evolution built upon a novel Viewpoint-Pathway collaboration. First, we employ multi-view image alignment to enhance fine-grained matching via multi-scale and multi-directional perspectives. Then, a bidirectional contrastive learning strategy generates "hard queries" and establishes complementary learning paths for visual and textual disambiguation to rebalance supervision. Finally, the model-state summary from the above collaboration is fed into an LLM meta-controller, which adaptively adjusts the training curriculum using expert knowledge to promote the model's evolution. On ViDoRe V2 and MMEB (VisDoc), Evo-Retriever achieves state-of-the-art performance, with nDCG@5 scores of 65.2 % and 77.1 %.

Fanqi Yu, Matteo Tiezzi, Tommaso Apicella, Cigdem Beyan, Vittorio Murino

We introduce a lifelong imitation learning framework that enables continual policy refinement across sequential tasks under realistic memory and data constraints. Our approach departs from conventional experience replay by operating entirely in a multimodal latent space, where compact representations of visual, linguistic, and robot's state information are stored and reused to support future learning. To further stabilize adaptation, we introduce an incremental feature adjustment mechanism that regularizes the evolution of task embeddings through an angular margin constraint, preserving inter-task distinctiveness. Our method establishes a new state of the art in the LIBERO benchmarks, achieving 10-17 point gains in AUC and up to 65% less forgetting compared to previous leading methods. Ablation studies confirm the effectiveness of each component, showing consistent gains over alternative strategies. The code is available at: https://github.com/yfqi/lifelong_mlr_ifa.

Minxing Luo, Linlong Fan, Qiushi Wang, Ge Wu, Yiyan Luo, Yuhang Yu, Jinwei Chen, Yaxing Wang, Qingnan Fan, Jian Yang

Current image super-resolution methods show strong performance on natural images but distort text, creating a fundamental trade-off between image quality and textual readability. To address this, we introduce **TIGER** (**T**ext-**I**mage **G**uided sup**E**r-**R**esolution), a novel two-stage framework that breaks this trade-off through a *"text-first, image-later"* paradigm. TIGER explicitly decouples glyph restoration from image enhancement: it first reconstructs precise text structures and uses them to guide full-image super-resolution. This ensures high fidelity and readability. To support comprehensive training and evaluation, we present the UZ-ST (UltraZoom-ST) dataset, the first Chinese scene text dataset with extreme zoom. Extensive experiments show TIGER achieves state-of-the-art performance, enhancing readability and image quality.

Qunjie Huang, Weina Zhu

Cross-subject EEG-to-image retrieval for visual decoding is challenged by subject shift and hubness in the embedding space, which distort similarity geometry and destabilize top-k rankings, making small-k shortlists unreliable. We introduce SATTC (Structure-Aware Test-Time Calibration), a label-free calibration head that operates directly on the similarity matrix of frozen EEG and image encoders. SATTC combines a geometric expert-subject-adaptive whitening of EEG embeddings with an adaptive variant of Cross-domain Similarity Local Scaling (CSLS)--and a structural expert built from mutual nearest neighbors, bidirectional top-k ranks, and class popularity, fused via a simple Product-of-Experts rule. On THINGS-EEG under a strict leave-one-subject-out protocol, standardized inference with cosine similarities, l2-normalized embeddings, and candidate whitening already yields a strong cross-subject baseline over the original ATM retrieval setup. Building on this baseline, SATTC further improves Top-1 and Top-5 accuracy, reduces hubness and per-class imbalance, and produces more reliable small-k shortlists. These gains transfer across multiple EEG encoders, supporting SATTC as an encoder-agnostic, label-free test-time calibration layer for cross-subject neural decoding. Code is available at https://github.com/QunjieHuang/SATTC-CVPR2026

Xin Hu, Ke Qin, Wen Yin, Yuan-Fang Li, Ming Li, Tao He

Scene Graph Generation (SGG) unifies object localization and visual relationship reasoning by predicting boxes and subject-predicate-object triples. Yet most pipelines treat SGG as a one-shot, deterministic classification instead of a genuine progressive, generative task. We propose FlowSG, which recasts SGG as continuous-time transport on a hybrid discrete-continuous state: starting from a noised graph , the model progressively grows an image-conditioned scene graph through constraint-aware refinements that jointly synthesize nodes (objects) and edges (predicates). Specifically, we first leverage a VQ-VAE to quantize a scene graph (e.g., the continuous visual features) into compact, predictable tokens; a graph Transformer then (i) predicts a conditional velocity field to transport continuous geometry (boxes) and (ii) updates discrete posteriors for categorical tokens (object features and predicate labels), coupling semantics and geometry via flow-conditioned message aggregation. Training combines flow-matching losses for geometry with a discrete-flow objective for tokens, yielding few-step inference and plug-and-play compatibility with standard detectors/segmenters. Extensive experiments on VG and PSG under closed- and open-vocabulary protocols show consistent gains in predicate R/mR and graph-level metrics, validating the mixed discrete-continuous generative formulation over one-shot classification baselines, e.g., an average improvement of about 3 points over the SOTA USG-Par.

Shannan Yan, Leqi Zheng, Keyu Lv, Jingchen Ni, Hongyang Wei, Jiajun Zhang, Guangting Wang, Jing LYU, Chun Yuan, Fengyun Rao

We study the task of establishing object-level visual correspondence across different viewpoints in videos, focusing on the challenging egocentric-to-exocentric and exocentric-to-egocentric scenarios. We propose a simple yet effective framework based on conditional binary segmentation, where an object query mask is encoded into a latent representation to guide the localization of the corresponding object in a target video. To encourage robust, view-invariant representations, we introduce a cycle-consistency training objective: the predicted mask in the target view is projected back to the source view to reconstruct the original query mask. This bidirectional constraint provides a strong self-supervisory signal without requiring ground-truth annotations and enables test-time training (TTT) at inference. Experiments on the Ego-Exo4D and HANDAL-X benchmarks demonstrate the effectiveness of our optimization objective and TTT strategy, achieving state-of-the-art performance. The code is available at https://github.com/shannany0606/CCMP.